From 95fd4448ba287676078d7e12cbf3a57e61289f69 Mon Sep 17 00:00:00 2001 From: Chaoyu Date: Mon, 26 Feb 2024 15:13:27 -0800 Subject: [PATCH] docs: add 2.0 proposal note (#506) --- README.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index ab6d50dc..3364b963 100644 --- a/README.md +++ b/README.md @@ -3,19 +3,21 @@ [![actions_status](https://github.com/bentoml/yatai/workflows/Release/badge.svg)](https://github.com/bentoml/yatai/actions) [![join_slack](https://badgen.net/badge/Join/Community%20Slack/cyan?icon=slack&style=flat-square)](https://join.slack.bentoml.org) +⚠️ Yatai for [BentoML 1.2](https://github.com/bentoml/BentoML/releases/tag/v1.2.0) is currently under construction. See [Yatai 2.0 Proposal](https://github.com/bentoml/Yatai/issues/504) for more details. + +--- + Yatai (屋台, food cart) is the Kubernetes deployment operator for [BentoML](https://github.com/bentoml/bentoml). It let DevOps teams to seamlessly integrate BentoML into their GitOps workflow, for deploying and scaling Machine Learning services on any Kubernetes cluster. -✨ Yatai contains a substantial subset of scalability features offered in [BentoCloud](https://l.bentoml.com/bento-cloud). For enterprise users looking for more advanced performance optimization and ease-of-use operational features, please [get in touch with us](https://kdyvd8c5ifq.typeform.com/to/eTujPAaE). - 👉 [Join our Slack community today!](https://l.bentoml.com/join-slack) --- ## Why Yatai? -Yatai is designed to run [BentoML](https://github.com/bentoml) on a distributed system, optimized for scalability and DevOps workflow. +Yatai empowers developers to deploy [BentoML](https://github.com/bentoml) on Kubernetes, optimized for CI/CD and DevOps workflow. Yatai is Cloud native and DevOps friendly. Via its Kubernetes-native workflow, specifically the [BentoDeployment CRD](https://docs.yatai.io/en/latest/concepts/bentodeployment_crd.html) (Custom Resource Definition), DevOps teams can easily fit BentoML powered services into their existing workflow.